
# !pip install plotly==5.3.1
# !pip install xgboost==1.3.3
# !brew install libomp
# !pip install tensorflow
# !pip install hyperopt


import numpy as np
import pandas as pd
import seaborn as sns
from matplotlib import pyplot as plt
from matplotlib import rcParams
import plotly.express as px
from sklearn.impute import SimpleImputer
from sklearn.model_selection import train_test_split, cross_val_score, GridSearchCV
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import f1_score,accuracy_score,classification_report, recall_score
from sklearn import tree
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
from sklearn.svm import SVC
from sklearn.model_selection import GridSearchCV
from sklearn.inspection import permutation_importance
from sklearn import decomposition
import xgboost as xgb
from xgboost import XGBClassifier
from hyperopt import STATUS_OK, Trials, fmin, hp, tpe, space_eval
from sklearn.ensemble import AdaBoostClassifier
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation,Dropout
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.callbacks import EarlyStopping
from sklearn.model_selection import GridSearchCV
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation,Dropout
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.callbacks import EarlyStopping
import pickle
import time


df = pd.read_csv('cardio_train.csv',sep=';')
df.head()


df.describe()


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 70000 entries, 0 to 69999
Data columns (total 13 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   id           70000 non-null  int64  
 1   age          70000 non-null  int64  
 2   gender       70000 non-null  int64  
 3   height       70000 non-null  int64  
 4   weight       70000 non-null  float64
 5   ap_hi        70000 non-null  int64  
 6   ap_lo        70000 non-null  int64  
 7   cholesterol  70000 non-null  int64  
 8   gluc         70000 non-null  int64  
 9   smoke        70000 non-null  int64  
 10  alco         70000 non-null  int64  
 11  active       70000 non-null  int64  
 12  cardio       70000 non-null  int64  
dtypes: float64(1), int64(12)
memory usage: 6.9 MB


df.isnull().sum()

id             0
age            0
gender         0
height         0
weight         0
ap_hi          0
ap_lo          0
cholesterol    0
gluc           0
smoke          0
alco           0
active         0
cardio         0
dtype: int64


df['cardio'].value_counts()

0    35021
1    34979
Name: cardio, dtype: int64


fig = px.histogram(df['cardio'], color=df['cardio'])
fig.update_layout(bargap=0.2)
fig.show()


# Drop id column as it is not useful 
df = df.drop('id', axis=1)
df


# Check for duplicated dataset
df[df.duplicated(keep=False)].sort_values(by=['gender', 'height', 'weight'], ascending= False).head()


# Remove duplicated dataset as it doesn't contribute to prediction but just increase size of training data 
df = df.drop_duplicates(keep = 'first')
df


# Converting age from days to years
df['year'] = (df['age']/365).round().astype('int')
df

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/1379977146.py:2: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy


# Reorder columns
df = df.drop('age', axis=1)
df = df[ ['year'] + [ col for col in df.columns if col != 'year' ] ]


#ap_lo and ap_hi cannot be negative or 0, firstly we set these error values with np.nan and then see what to do with these error values
df['ap_hi'].loc[(df['ap_hi']<=0)]=np.nan
df['ap_lo'].loc[(df['ap_lo']<=0)]=np.nan
df


#ap_lo cannot be greater than ap_hi, firstly we set these error values with np.nan and then see what to do with these error values
df['ap_lo'].loc[(df['ap_lo'])>=(df['ap_hi'])]=0

#change the corresponding ap_hi to np.nan
df['ap_hi'].loc[(df['ap_lo'])==0]=np.nan


#Now all the error values are been as nan, then we check the number of null value
df.isnull().sum()

year              0
gender            0
height            0
weight            0
ap_hi          1236
ap_lo          1251
cholesterol       0
gluc              0
smoke             0
alco              0
active            0
cardio            0
dtype: int64


#Since there are thousands of values are null, it could be a waste if we drop them all, so we decide to replace this value with median
#We choose median becasue median is not easy to be affected by outliers

##from sklearn.impute import SimpleImputer
ap_hi=df.loc[:,"ap_hi"].values.reshape(-1,1)
ap_hi_median = SimpleImputer()
ap_hi_median=ap_hi_median.fit_transform(ap_hi)
df.loc[:,"ap_hi"]=ap_hi_median

ap_lo=df.loc[:,"ap_lo"].values.reshape(-1,1)
ap_lo_median = SimpleImputer()
ap_lo_median=ap_lo_median.fit_transform(ap_lo)
df.loc[:,"ap_lo"]=ap_lo_median

df.isnull().sum()

year           0
gender         0
height         0
weight         0
ap_hi          0
ap_lo          0
cholesterol    0
gluc           0
smoke          0
alco           0
active         0
cardio         0
dtype: int64


# Plotting weight against height to have a big picture of the data distribution and outliers
fig = px.scatter(df, x="weight", y="height")
fig.show()


# Plotting ap_lo against ap_hi to have a big picture of the data distribution and outliers
fig = px.scatter(df, x="ap_lo", y="ap_hi")
fig.show()


# Defining a function to keep track of the number of outliers 
def outliers(df_out,columns, drop = False):
    for each_feature in columns:
        feature_data = df_out[each_feature]
        Q1 = np.percentile(feature_data, 25.) # 25th percentile of the data of the given feature
        Q3 = np.percentile(feature_data, 75.) # 75th percentile of the data of the given feature
        IQR = Q3-Q1 #Interquartile Range
        outlier_step = IQR * 1.5 #That's we were talking about above
        outliers = feature_data[~((feature_data >= Q1 - outlier_step) & (feature_data <= Q3 + outlier_step))].index.tolist()
        if (drop == True):
            df_out.drop(outliers, inplace=True)
            print('Filtering through feature {}, No of Outliers removed is {}'.format(each_feature, len(outliers)))
            continue  
        print('For the feature {}, No of Outliers is {}'.format(each_feature, len(outliers)))

outliers(df,['height', 'weight', 'ap_hi', 'ap_lo'])

For the feature height, No of Outliers is 519
For the feature weight, No of Outliers is 1819
For the feature ap_hi, No of Outliers is 1058
For the feature ap_lo, No of Outliers is 3548


# Logarithm function helps us to correct skewness of data and allows us to remove the appropriate outliers besides scaling down the data and reduce data loss
trial_df = df.copy()
trial_df["ap_hi_logged"] = np.log(trial_df["ap_hi"])
print('skewness of ap_hi before log: ', trial_df['ap_hi'].skew())
print('skewness of ap_hi after log: ', trial_df['ap_hi_logged'].skew())

skewness of ap_hi before log:  85.58924279640866
skewness of ap_hi after log:  5.734343654420562


outlier_free_df = df.copy()
outlier_free_df[['height', 'weight']] = np.log(outlier_free_df[['height', 'weight']])
outliers(outlier_free_df, ['height', 'weight'], drop=True)

Filtering through feature height, No of Outliers removed is 484
Filtering through feature weight, No of Outliers removed is 1115


# number of removed datapoints
print('Number of datapoints removed is', len(df)-len(outlier_free_df))

Number of datapoints removed is 1599


# getting back the original height and weight values
outlier_free_df[['height', 'weight']] = df[['height', 'weight']]
# Reassigning outlier_free_df to df
df=outlier_free_df


# A study published in 1995 recorded maximum blood pressure of 370/360 mm Hg
# Diastolic pressure (ap_lo) should not be 0, there should be blood pressure for blood flow
df.drop(df[df['ap_hi']>370].index, inplace=True)
print('Number of points remaining is', len(df))
print('Number of points removed is', 68377-len(df))

Number of points remaining is 68340
Number of points removed is 37


df[['height', 'weight', 'ap_hi', 'ap_lo']].describe()


#Create 'bmi' column and move it to the proper position
#BMI=w/(h^2), where w is weight(kg), h is height(m)
df['BMI']= df['weight']/(df['height']*df['height']/10000)
df.insert(8,'bmi',df['BMI'])
del df['BMI']

#Create 'map' column and move it to the proper position
#mean arterial pressure (MAP) = (ap_hi + 2 *(ap_lo))/3
df['MAP']=(df['ap_hi']+2*df['ap_lo'])/3
df.insert(6,'map',df['MAP'])
del df['MAP']

#Create 'pp' column and move it to the proper position
#Pulse pressure (PP) = ap_hi-ap_lo
df['PP']= df['ap_hi']-df['ap_lo']
df.insert(7,'pp',df['PP'])
del df['PP']

#Make gender label in 0 and 1 instead of 1 and 2
df['gender'] = df['gender'] - 1


# Categorical Variables
dfCatData = pd.DataFrame(df[['gender', 'cholesterol', 'gluc', 'smoke','alco','cardio','active']])
dfCatData.head()


dfCatData['gender'] = dfCatData['gender'].astype('category')
dfCatData['cholesterol'] = dfCatData['cholesterol'].astype('category')
dfCatData['gluc'] = dfCatData['gluc'].astype('category')
dfCatData['smoke'] = dfCatData['smoke'].astype('category')
dfCatData['alco'] = dfCatData['alco'].astype('category')
dfCatData['cardio'] = dfCatData['cardio'].astype('category')
dfCatData['active'] = dfCatData['active'].astype('category')


# Numerical Variables
dfnum = pd.DataFrame(df[['year','height','weight','ap_hi','ap_lo','pp','map','bmi']])


f, axes = plt.subplots(8, 3, figsize=(30, 35))
colors = ["red", "green", "blue", "magenta", "cyan", "yellow", "purple", "orange"]

count = 0
for var in dfnum:
    sns.boxplot(data=dfnum[var], orient = "h", color = colors[count], ax = axes[count,0])
    sns.histplot(data=dfnum[var], color = colors[count], ax = axes[count,1])
    sns.violinplot(data=dfnum[var], color = colors[count], ax = axes[count,2])
    count += 1


fig = px.histogram(df, x="year", pattern_shape="cardio")
fig.update_layout(bargap=0.2)
fig.show()


#to make our dataset fit our objective more, and make our objective more targeted. we decide to drop the year == 30, and make the objectove to target 39-65 aged people. 
df = df[df.year>=35]


fig = px.histogram(df, x="year", pattern_shape="cardio")
fig.update_layout(bargap=0.2)
fig.show()


trenddf = pd.DataFrame(df.groupby(['year'])['cardio'].sum()/df.groupby(['year']).size(), columns=['risk']).reset_index()
fig = px.line(trenddf, x="year", y="risk",title='The risk of cardiovascular disease varies with age')
fig.show()


fig = px.box(df, x="cardio", y="year",color = 'cardio')
fig.update_traces(quartilemethod="exclusive") # or "inclusive", or "linear" by default
fig.show()


fig = px.box(df, x="cardio", y="height",color = 'cardio')
fig.update_traces(quartilemethod="exclusive") # or "inclusive", or "linear" by default
fig.show()


fig = px.box(df, x="cardio", y="weight",color = 'cardio')
fig.update_traces(quartilemethod="exclusive") # or "inclusive", or "linear" by default
fig.show()


fig = px.box(df, x="cardio", y="ap_hi",color = 'cardio')
fig.update_traces(quartilemethod="exclusive") # or "inclusive", or "linear" by default
fig.show()


fig = px.box(df, x="cardio", y="ap_lo",color = 'cardio')
fig.update_traces(quartilemethod="exclusive") # or "inclusive", or "linear" by default
fig.show()


fig = px.box(df, x="cardio", y="pp",color = 'cardio')
fig.update_traces(quartilemethod="exclusive") # or "inclusive", or "linear" by default
fig.show()


fig = px.box(df, x="cardio", y="map",color = 'cardio')
fig.update_traces(quartilemethod="exclusive") # or "inclusive", or "linear" by default
fig.show()


fig = px.box(df, x="cardio", y="bmi",color = 'cardio')
fig.update_traces(quartilemethod="exclusive") # or "inclusive", or "linear" by default
fig.show()


df_uniques = pd.melt(frame=df, value_vars=['gender','cholesterol', 
                                           'gluc', 'smoke', 'alco', 
                                           'active', 'cardio'])
df_uniques = pd.DataFrame(df_uniques.groupby(['variable', 
                                              'value'])['value'].count()) \
    .sort_index(level=[0, 1]) \
    .rename(columns={'value': 'count'}) \
    .reset_index()

sns.factorplot(x='variable', y='count', hue='value', 
               data=df_uniques, kind='bar', height=12);

C:\YongHao\Anaconda\envs\dsai\lib\site-packages\seaborn\categorical.py:3717: UserWarning:

The `factorplot` function has been renamed to `catplot`. The original name will be removed in a future release. Please update your code. Note that the default `kind` in `factorplot` (`'point'`) has changed `'strip'` in `catplot`.


trenddf = pd.DataFrame(df.groupby(['gender','year'])['cardio'].sum()/df.groupby(['gender','year']).size(), columns=['risk']).reset_index()
trenddf['gender'] = trenddf['gender'].map({0: 'female', 1: 'male'})
fig = px.line(trenddf, x="year", y="risk",color='gender',title='The risk of cardiovascular disease varies by gender with age', labels={'female','male'})
fig.show()


fig = px.histogram(dfCatData, x="gender", color="gender", pattern_shape="cardio")
fig.update_layout(bargap=0.2)
fig.show()


trenddf = pd.DataFrame(df.groupby(['cholesterol','year'])['cardio'].sum()/df.groupby(['cholesterol','year']).size(), columns=['risk']).reset_index()
trenddf['cholesterol'] = trenddf['cholesterol'].map({ 1: 'normal', 2: 'above normal', 3: 'well above normal'})
fig = px.line(trenddf, x="year", y="risk",color='cholesterol',title='The risk of cardiovascular disease varies by cholesterol with age')
fig.show()


fig = px.histogram(dfCatData, x="cholesterol", color="cholesterol", pattern_shape="cardio")
fig.update_layout(bargap=0.2)
fig.show()


trenddf = pd.DataFrame(df.groupby(['gluc','year'])['cardio'].sum()/df.groupby(['gluc','year']).size(), columns=['risk']).reset_index()
trenddf['gluc'] = trenddf['gluc'].map({ 1: 'normal', 2: 'above normal', 3: 'well above normal'})
fig = px.line(trenddf, x="year", y="risk",color='gluc',title='The risk of cardiovascular disease varies by gluc with age')
fig.show()


fig = px.histogram(dfCatData, x="gluc", color="gluc", pattern_shape="cardio")
fig.update_layout(bargap=0.2)
fig.show()


trenddf = pd.DataFrame(df.groupby(['smoke','year'])['cardio'].sum()/df.groupby(['smoke','year']).size(), columns=['risk']).reset_index()
trenddf['smoke'] = trenddf['smoke'].map({ 0: 'nonsmoker', 1: 'smoker'})
fig = px.line(trenddf, x="year", y="risk",color='smoke',title='The risk of cardiovascular disease varies by smoking with age')
fig.show()


fig = px.histogram(dfCatData, x="smoke", color="smoke", pattern_shape="cardio")
fig.update_layout(bargap=0.2)
fig.show()


dfCatData['smoke'].value_counts()

0    62334
1     6006
Name: smoke, dtype: int64


# Undersampling people with 'smoke' == 0 to have a more reliable analysis
num_smoke = int(len(df[df['smoke'] == 1]))
non_smoke_indices = df[df.smoke == 0].index
random_indices = np.random.choice(non_smoke_indices,num_smoke, replace=False)
smoke_indices = df[df.smoke == 1].index
under_sample_indices = np.concatenate([smoke_indices,random_indices])
under_sample = df.loc[under_sample_indices]
%matplotlib inline
sns.countplot(x='smoke', data=under_sample)

<AxesSubplot:xlabel='smoke', ylabel='count'>


trenddf = pd.DataFrame(under_sample.groupby(['smoke','year'])['cardio'].sum()/under_sample.groupby(['smoke','year']).size(), columns=['risk']).reset_index()
trenddf['smoke'] = trenddf['smoke'].map({ 0: 'nonsmoker', 1: 'smoker'})
fig = px.line(trenddf, x="year", y="risk",color='smoke',title='The risk of cardiovascular disease varies by smoking with age')
fig.show()


df = df.drop('smoke', axis=1)


trenddf = pd.DataFrame(df.groupby(['alco','year'])['cardio'].sum()/df.groupby(['alco','year']).size(), columns=['risk']).reset_index()
trenddf['alco'] = trenddf['alco'].map({ 0: 'non-drinker', 1: 'drinker'})
fig = px.line(trenddf, x="year", y="risk",color='alco',title='The risk of cardiovascular disease varies by alco with age')
fig.show()


fig = px.histogram(dfCatData, x="alco", color="alco", pattern_shape="cardio")
fig.update_layout(bargap=0.2)
fig.show()


dfCatData['alco'].value_counts()

0    64680
1     3660
Name: alco, dtype: int64


# Undersampling people with 'smoke' == 0 to have a more reliable analysis
num_alco = int(len(df[df['alco'] == 1]))
non_alco_indices = df[df.alco == 0].index
random_indices = np.random.choice(non_alco_indices,num_alco, replace=False)
alco_indices = df[df.alco == 1].index
under_sample_indices = np.concatenate([alco_indices,random_indices])
under_sample = df.loc[under_sample_indices]
%matplotlib inline
sns.countplot(x='alco', data=under_sample)

<AxesSubplot:xlabel='alco', ylabel='count'>


trenddf = pd.DataFrame(under_sample.groupby(['alco','year'])['cardio'].sum()/under_sample.groupby(['alco','year']).size(), columns=['risk']).reset_index()
trenddf['alco'] = trenddf['alco'].map({ 0: 'non-drinker', 1: 'drinker'})
fig = px.line(trenddf, x="year", y="risk",color='alco',title='The risk of cardiovascular disease varies by alco with age')
fig.show()


df = df.drop('alco', axis=1)


trenddf = pd.DataFrame(df.groupby(['active','year'])['cardio'].sum()/df.groupby(['active','year']).size(), columns=['risk']).reset_index()
trenddf['active'] = trenddf['active'].map({ 0: 'inactive', 1: 'active'})
fig = px.line(trenddf, x="year", y="risk",color='active',title='The risk of cardiovascular disease varies by active with age')
fig.show()


fig = px.histogram(dfCatData, x="active", color="active", pattern_shape="cardio")
fig.update_layout(bargap=0.2)
fig.show()


heatmap_df = pd.concat([dfnum, df['cardio']], axis=1)
corr_matrix = heatmap_df.corr()
plt.subplots(figsize = (12, 10))
sns.heatmap(corr_matrix, annot = True, fmt = ".2f")
plt.show()


target_value = df['cardio']
cleaned_data_for_pca = df.drop(['cardio'], axis=1)


scaled_data = StandardScaler().fit_transform(cleaned_data_for_pca) # Have to scale, PCA's output is influenced based on the scale of the features of the data.

pca = decomposition.PCA()
pca.n_components = 2
pca_data = pca.fit_transform(scaled_data)

pca_data = np.vstack((pca_data.T, target_value)).T # concatenate with target values
pca_df = pd.DataFrame(data = pca_data, columns = ('principal component 1', 'principal component 2', 'label'))
#pca_df['label']=pca_df['label'].map({0.0: 'No Disease', 1: 'Has Disease'})

pca_df


cleaned_data_for_pca.columns

Index(['year', 'gender', 'height', 'weight', 'ap_hi', 'ap_lo', 'map', 'pp',
       'cholesterol', 'gluc', 'bmi', 'active'],
      dtype='object')


# Shows explained variance of each feature in each component (corrseponding to the column names)
pca.components_

array([[ 0.15861127,  0.04033664,  0.01409833,  0.272979  ,  0.49092817,
         0.41889317,  0.48728598,  0.3556982 ,  0.17883624,  0.11354017,
         0.27048933, -0.00317441],
       [-0.15799988,  0.58871976,  0.62290437,  0.0491057 ,  0.07576417,
         0.094145  ,  0.0921477 ,  0.03103695, -0.26812325, -0.24333521,
        -0.28782849,  0.00430624]])


print("Principal Component 1 Variables with highest explained variance: ")
var_ls1 = list(cleaned_data_for_pca.columns)
pc1 = list(pca.components_[0])
i = np.argmax(pc1)
pc1.pop(np.argmax(pc1))
print('1', var_ls1[i])
var_ls1.pop(i)
j = np.argmax(pc1)
pc1.pop(np.argmax(pc1))
print('2', var_ls1[j])
var_ls1.pop(j)
k = np.argmax(pc1)
pc1.pop(np.argmax(pc1))
print('3', var_ls1[k])
var_ls1.pop(k)
l = np.argmax(pc1)
pc1.pop(np.argmax(pc1))
print('4', var_ls1[l])

Principal Component 1 Variables with highest explained variance: 
1 ap_hi
2 map
3 ap_lo
4 pp


print('Explained variation per principal component: {}'.format(pca.explained_variance_ratio_))

Explained variation per principal component: [0.29795739 0.14095567]


fig = px.scatter(pca_df, x='principal component 1', y='principal component 2', color=pca_df['label'])
fig.show()


data = pd.read_csv('diabetes.csv')
data.head()


# First, the 0 values are replaced with null values
data[['Glucose','BloodPressure','SkinThickness','Insulin','BMI']] = data[['Glucose','BloodPressure','SkinThickness','Insulin','BMI']].replace(0,np.NaN)


data.isnull().sum()

Pregnancies                   0
Glucose                       5
BloodPressure                35
SkinThickness               227
Insulin                     374
BMI                          11
DiabetesPedigreeFunction      0
Age                           0
Outcome                       0
dtype: int64


# The missing values will be filled with the median values of each variable.
def median_target(var):   
    temp = data[data[var].notnull()]
    temp = temp[[var, 'Outcome']].groupby(['Outcome'])[[var]].median().reset_index()
    return temp


# The values to be given for incomplete observations are given the median value of people who are not sick and the median values of people who are sick.
columns = data.columns
columns = columns.drop("Outcome")
for i in columns:
    median_target(i)
    data.loc[(data['Outcome'] == 0 ) & (data[i].isnull()), i] = median_target(i)[i][0]
    data.loc[(data['Outcome'] == 1 ) & (data[i].isnull()), i] = median_target(i)[i][1]


data.isnull().sum()

Pregnancies                 0
Glucose                     0
BloodPressure               0
SkinThickness               0
Insulin                     0
BMI                         0
DiabetesPedigreeFunction    0
Age                         0
Outcome                     0
dtype: int64


data.head(2)


df.head(2)


corr_matrix = data.corr()
plt.subplots(figsize = (12, 10))
sns.heatmap(corr_matrix, annot = True, fmt = ".2f")
plt.show()


#rename the feature to make them be consistent with those of the cardio dataset. (Important for model training)
data.rename(columns={'BloodPressure':'map'},inplace=True)
data.rename(columns={'BMI':'bmi'},inplace=True)
data.rename(columns={'Age':'year'},inplace=True)


data.columns

Index(['Pregnancies', 'Glucose', 'map', 'SkinThickness', 'Insulin', 'bmi',
       'DiabetesPedigreeFunction', 'year', 'Outcome'],
      dtype='object')


data.describe()


df.describe()


#In order to make the diabetes dataset good fit to our cardio dataset, we would like to drop the objects aged below 39 in diabetes dataset 
data.drop(data[data['year']<39].index, inplace=True)


data.describe()


#check
data.head(2)


data['Outcome'].value_counts()

1    111
0    108
Name: Outcome, dtype: int64


#check
data_for_merge= pd.DataFrame(df[['map','bmi','year']])


data_for_merge.head(1)


# Now, it is time to train the model, here we use randomforest classifier
# Extract Response and Predictors
y = pd.DataFrame(data['Outcome'])
X = pd.DataFrame(data[['map','bmi','year']]) 

# Split the Dataset into Train and Test
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state=99)


#adjust the max_depth parameter to hance the accuracy
score1=[]
for i in range(0,30):
    rfc1=RandomForestClassifier(max_depth=i+1,n_jobs=-1,random_state=90)
    rfc1.fit(X_train,y_train)
    pred = rfc1.predict(X_test)
    score = 100*np.round(accuracy_score(y_test,pred),decimals=4)
    score1.append(score)
    
print(" The best accuracy is" , max(score1))
print(" Occur at max_depth = ",(score1.index(max(score1))+1))
plt.figure(figsize=[20,5])
n_est=(score1.index(max(score1))+1)

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/2401713133.py:5: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().

 The best accuracy is 65.14999999999999
 Occur at max_depth =  5

<Figure size 1440x360 with 0 Axes>


RFC=RandomForestClassifier(n_jobs=-1,random_state=90,max_depth=5)
RFC.fit(X_train,y_train)
pred = RFC.predict(X_test)
score = 100*np.round(accuracy_score(y_test,pred),decimals=4)
print("The accuracy is ", score,"%")

The accuracy is  65.14999999999999 %

C:\Users\YONGHA~1\AppData\Local\Temp/ipykernel_6308/1148034922.py:2: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().


pred_merge = RFC.predict(data_for_merge)


pred_merge = pd.DataFrame(pred_merge, columns = ["Diabetes"], index = df.index)
df.insert(12,'diabetes',pred_merge)


df.head(10)

df


# Only include contribute to model improvements
df_train = df[['year', 'gender', 'height', 'weight', 'ap_hi', 'ap_lo', 'map', 'pp', 'cholesterol', 'gluc', 'bmi', 'active', 'diabetes', 'cardio']]
df_train


df_train.columns

Index(['year', 'gender', 'height', 'weight', 'ap_hi', 'ap_lo', 'map', 'pp',
       'cholesterol', 'gluc', 'bmi', 'active', 'diabetes', 'cardio'],
      dtype='object')


# Spliting data into train set and test set
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

X_train, X_test, y_train, y_test = train_test_split(df_train.drop('cardio',axis=1),df_train.cardio,test_size=0.20, random_state=42)

# Scaling data: 
# in many machine learning algorithms, to bring all features in the same standing,
# we need to do scaling so that one significant number doesn’t impact the model just because of their large magnitude.
to_be_scaled_feat = ['year', 'height', 'weight', 'ap_hi', 'ap_lo', 'map', 'pp', 'bmi']
scaler=StandardScaler()
scaler.fit(X_train[to_be_scaled_feat])

# saving the scaler
filename = 'scaler.sav'
pickle.dump(scaler, open(filename, 'wb'))

X_train[to_be_scaled_feat] = scaler.transform(X_train[to_be_scaled_feat])
X_test[to_be_scaled_feat] = scaler.transform(X_test[to_be_scaled_feat])


# Import DecisionTreeClassifier model from Scikit-Learn
from sklearn.tree import DecisionTreeClassifier

# Decision Tree using Train Data
dectree = DecisionTreeClassifier(max_depth = 2)  # create the decision tree object
dectree.fit(X_train, y_train)                    # train the decision tree model

# Predict Legendary values corresponding to Total
y_train_pred = dectree.predict(X_train)
y_test_pred = dectree.predict(X_test)

# Check the Goodness of Fit (on Train Data)
print("Goodness of Fit of Model \tTrain Dataset")
print("Classification Accuracy \t:", dectree.score(X_train, y_train))
print()

# Check the Goodness of Fit (on Test Data)
print("Goodness of Fit of Model \tTest Dataset")
print("Classification Accuracy \t:", dectree.score(X_test, y_test))
print()

Goodness of Fit of Model 	Train Dataset
Classification Accuracy 	: 0.7132143118460526

Goodness of Fit of Model 	Test Dataset
Classification Accuracy 	: 0.7147351477904594


train_results = []
test_results = []

for x in range(1, 21):
    # Decision Tree using Train Data
    dectree = DecisionTreeClassifier(max_depth = x)  # create the decision tree object
    dectree.fit(X_train, y_train)                    # train the decision tree model

    # Predict Response corresponding to Predictors
    y_train_pred = dectree.predict(X_train)
    y_test_pred = dectree.predict(X_test)
    
    train_results.append(dectree.score(X_train, y_train))
    test_results.append(dectree.score(X_test, y_test))
    
best_max_depth = np.argmax(test_results) + 1
print('Best parameter is max_depth =', best_max_depth, 'with test classification accuracy =', np.max(test_results))
    
fig, axes = plt.subplots(1, 1, figsize=(12, 8))
sns.lineplot(x=[x for x in range(1, 21)], y=train_results, label='train')
sns.lineplot(x=[x for x in range(1, 21)], y=test_results, label='test')
plt.legend()
plt.xlabel('max_depth')
plt.ylabel('accuracy')
plt.show()

Best parameter is max_depth = 6 with test classification accuracy = 0.7297336845185836


# Getting our final improved model
dectree = DecisionTreeClassifier(max_depth = best_max_depth)  # create the decision tree object
dectree.fit(X_train, y_train)                                         # train the decision tree model

# Predict Legendary values corresponding to Total
y_train_pred = dectree.predict(X_train)
y_test_pred = dectree.predict(X_test)

# Plot the Confusion Matrix for Train and Test
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
print(classification_report(y_test, y_test_pred, digits=4))
f, axes = plt.subplots(1, 1, figsize=(8, 4))
axes.set_title('Test Set')
sns.heatmap(confusion_matrix(y_test, y_test_pred), 
           annot = True, fmt=".0f", annot_kws={"size": 18})

              precision    recall  f1-score   support

           0     0.7087    0.7866    0.7457      6880
           1     0.7566    0.6724    0.7120      6788

    accuracy                         0.7299     13668
   macro avg     0.7327    0.7295    0.7288     13668
weighted avg     0.7325    0.7299    0.7289     13668

<AxesSubplot:title={'center':'Test Set'}>


# Plot the trained Decision Tree
from sklearn.tree import plot_tree
fig, ax = plt.subplots(figsize=(20, 20))
out = plot_tree(dectree, 
          feature_names = X_train.columns,
          class_names = [str(x) for x in dectree.classes_],
          filled=True)

for o in out:
    arrow = o.arrow_patch
    if arrow is not None:
        arrow.set_edgecolor('black')
        arrow.set_linewidth(3)
        
plt.show()


dectree.feature_importances_

array([1.21849517e-01, 0.00000000e+00, 1.23098803e-03, 6.15060849e-03,
       7.68999886e-01, 5.06503902e-04, 1.39559120e-03, 4.90818698e-03,
       7.16704194e-02, 5.99808881e-03, 1.53754144e-02, 1.91479578e-03,
       0.00000000e+00])


# Plotting feature importances
importance_dectree=pd.DataFrame([*zip(X_train.columns,dectree.feature_importances_)],columns=['feature_name','importance'])
plot_order = importance_dectree['importance'].sort_values(ascending=False).index.values
ls = []
for x in plot_order:
    ls.append(importance_dectree['feature_name'][x])
fig, ax = plt.subplots(figsize=(20, 20))
sns.barplot(x = "feature_name", y="importance",data = importance_dectree, order=ls)

<AxesSubplot:xlabel='feature_name', ylabel='importance'>


# tuning n_estimators for best performance
train_results = []
test_results = []

for x in range(1, 101):
    # Random Forest using Train Data
    rfc = RandomForestClassifier(n_estimators=x,n_jobs=-1,random_state=90)  # create the random forest object
    rfc.fit(X_train, y_train)                                                 # train the random forest model

    # Predict Response corresponding to Predictors
    y_train_pred = rfc.predict(X_train)
    y_test_pred = rfc.predict(X_test)
    
    train_results.append(rfc.score(X_train, y_train))
    test_results.append(rfc.score(X_test, y_test))
    
best_n_est = np.argmax(test_results) + 1
print('Best parameter is n_estimators =', best_n_est, 'with test classification accuracy =', np.max(test_results))
    
fig, axes = plt.subplots(1, 1, figsize=(12, 8))
sns.lineplot(x=[x for x in range(1, 101)], y=train_results, label='train')
sns.lineplot(x=[x for x in range(1, 101)], y=test_results, label='test')
plt.legend()
plt.xlabel('n_estimators')
plt.ylabel('accuracy')
plt.show()

Best parameter is n_estimators = 99 with test classification accuracy = 0.7032484635645303


# tuning max_depth for best performance
train_results = []
test_results = []

for x in range(1, 21):
    # Random Forest using Train Data
    rfc = RandomForestClassifier(max_depth=x,n_jobs=-1,random_state=90)  # create the random forest object
    rfc.fit(X_train, y_train)                                                 # train the random forest model

    # Predict Response corresponding to Predictors
    y_train_pred = rfc.predict(X_train)
    y_test_pred = rfc.predict(X_test)
    
    train_results.append(rfc.score(X_train, y_train))
    test_results.append(rfc.score(X_test, y_test))
    
best_depth = np.argmax(test_results) + 1
print('Best parameter is max_depth =', best_depth, 'with test classification accuracy =', np.max(test_results))
    
fig, axes = plt.subplots(1, 1, figsize=(12, 8))
sns.lineplot(x=[x for x in range(1, 21)], y=train_results, label='train')
sns.lineplot(x=[x for x in range(1, 21)], y=test_results, label='test')
plt.legend()
plt.xlabel('max_depth')
plt.ylabel('accuracy')
plt.show()

Best parameter is max_depth = 11 with test classification accuracy = 0.7342698273339187


# tuning min_samples_split for best performance
train_results = []
test_results = []

for x in range(40, 71):
    # Random Forest using Train Data
    rfc = RandomForestClassifier(min_samples_split=x,n_jobs=-1,random_state=90)  # create the random forest object
    rfc.fit(X_train, y_train)                                                 # train the random forest model

    # Predict Response corresponding to Predictors
    y_train_pred = rfc.predict(X_train)
    y_test_pred = rfc.predict(X_test)
    
    train_results.append(rfc.score(X_train, y_train))
    test_results.append(rfc.score(X_test, y_test))
    
best_mss = np.argmax(test_results) + 40
print('Best parameter is min_samples_split =', best_mss, 'with test classification accuracy =', np.max(test_results))
    
fig, axes = plt.subplots(1, 1, figsize=(12, 8))
sns.lineplot(x=[x for x in range(40, 71)], y=train_results, label='train')
sns.lineplot(x=[x for x in range(40, 71)], y=test_results, label='test')
plt.legend()
plt.xlabel('min_samples_split')
plt.ylabel('accuracy')
plt.show()

Best parameter is min_samples_split = 42 with test classification accuracy = 0.7333187006145742


# Getting best performing model
rfc=RandomForestClassifier(max_depth=best_depth, n_jobs=-1,random_state=90)
rfc.fit(X_train,y_train)
pred = rfc.predict(X_test)

# Plot the Confusion Matrix for Train and Test
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
print(classification_report(y_test, pred, digits=4))
f, axes = plt.subplots(1, 1, figsize=(8, 4))
axes.set_title('Test Set')
sns.heatmap(confusion_matrix(y_test, y_test_pred), 
           annot = True, fmt=".0f", annot_kws={"size": 18})

              precision    recall  f1-score   support

           0     0.7159    0.7827    0.7478      6880
           1     0.7568    0.6852    0.7192      6788

    accuracy                         0.7343     13668
   macro avg     0.7363    0.7339    0.7335     13668
weighted avg     0.7362    0.7343    0.7336     13668

<AxesSubplot:title={'center':'Test Set'}>


rfc.feature_importances_

array([0.10933635, 0.00596307, 0.0319506 , 0.04093034, 0.27043486,
       0.07722145, 0.19826993, 0.10985191, 0.07239483, 0.01258894,
       0.05610712, 0.00909823, 0.00585238])


X_train.columns

Index(['year', 'gender', 'height', 'weight', 'ap_hi', 'ap_lo', 'map', 'pp',
       'cholesterol', 'gluc', 'bmi', 'active', 'diabetes'],
      dtype='object')


# Plot feature importances
importance_ramdomforest=pd.DataFrame([*zip(X_train.columns,rfc.feature_importances_)],columns=['feature_name','importance'])
plot_order = importance_ramdomforest['importance'].sort_values(ascending=False).index.values
ls = []
for x in plot_order:
    ls.append(importance_ramdomforest['feature_name'][x])
fig, ax = plt.subplots(figsize=(20, 20))
sns.barplot(x = "feature_name", y="importance",data = importance_ramdomforest, order=ls)

<AxesSubplot:xlabel='feature_name', ylabel='importance'>


import warnings
warnings.filterwarnings("ignore", category=UserWarning)

def hyperopt_xgb_score(params):
    clf = XGBClassifier(**params)
    clf.fit(X_train, y_train)
    xgb_pred = clf.predict(X_test)
    current_score = accuracy_score(y_test, xgb_pred)
    print(current_score, params)
    loss = 1 - current_score # we set the loss as 1-score to enable fmin to minimise it
    return loss 
 
space_xgb = {
            'learning_rate': hp.quniform('learning_rate', 0, 0.05, 0.0001),
            'n_estimators': hp.choice('n_estimators', range(1, 1000)),
            'eta': hp.quniform('eta', 0.025, 0.5, 0.005),
            'max_depth':  hp.choice('max_depth', np.arange(2, 12, dtype=int)),
            'min_child_weight': hp.quniform('min_child_weight', 1, 9, 0.025),
            'subsample': hp.quniform('subsample', 0.5, 1, 0.005),
            'gamma': hp.quniform('gamma', 0.5, 1, 0.005),
            'colsample_bytree': hp.quniform('colsample_bytree', 0.5, 1, 0.005),
            'eval_metric': 'auc',
            'objective': 'binary:logistic',
            'booster': 'gbtree',
            'tree_method': 'exact',
            'missing': None
        }
 
best = fmin(fn=hyperopt_xgb_score, space=space_xgb, algo=tpe.suggest, max_evals=20)

0.7334650278021656                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.645, 'eta': 0.425, 'eval_metric': 'auc', 'gamma': 0.925, 'learning_rate': 0.0366, 'max_depth': 5, 'min_child_weight': 8.85, 'missing': None, 'n_estimators': 467, 'objective': 'binary:logistic', 'subsample': 0.625, 'tree_method': 'exact'}
0.7302458296751536                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.625, 'eta': 0.31, 'eval_metric': 'auc', 'gamma': 0.68, 'learning_rate': 0.0036000000000000003, 'max_depth': 3, 'min_child_weight': 3.9250000000000003, 'missing': None, 'n_estimators': 800, 'objective': 'binary:logistic', 'subsample': 0.92, 'tree_method': 'exact'}
0.7232221246707639                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.865, 'eta': 0.425, 'eval_metric': 'auc', 'gamma': 0.8200000000000001, 'learning_rate': 0.0296, 'max_depth': 2, 'min_child_weight': 6.625, 'missing': None, 'n_estimators': 60, 'objective': 'binary:logistic', 'subsample': 0.96, 'tree_method': 'exact'}
0.7249780509218613                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.8200000000000001, 'eta': 0.14, 'eval_metric': 'auc', 'gamma': 0.98, 'learning_rate': 0.041600000000000005, 'max_depth': 8, 'min_child_weight': 7.800000000000001, 'missing': None, 'n_estimators': 997, 'objective': 'binary:logistic', 'subsample': 0.7000000000000001, 'tree_method': 'exact'}
0.7329528826455955                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.64, 'eta': 0.145, 'eval_metric': 'auc', 'gamma': 0.8250000000000001, 'learning_rate': 0.0429, 'max_depth': 10, 'min_child_weight': 8.875, 'missing': None, 'n_estimators': 159, 'objective': 'binary:logistic', 'subsample': 0.5650000000000001, 'tree_method': 'exact'}
0.7311237928007024                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.705, 'eta': 0.33, 'eval_metric': 'auc', 'gamma': 0.5750000000000001, 'learning_rate': 0.0145, 'max_depth': 2, 'min_child_weight': 4.9750000000000005, 'missing': None, 'n_estimators': 666, 'objective': 'binary:logistic', 'subsample': 0.9400000000000001, 'tree_method': 'exact'}
0.7303189932689493                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.655, 'eta': 0.28, 'eval_metric': 'auc', 'gamma': 0.685, 'learning_rate': 0.0045000000000000005, 'max_depth': 4, 'min_child_weight': 8.3, 'missing': None, 'n_estimators': 313, 'objective': 'binary:logistic', 'subsample': 0.765, 'tree_method': 'exact'}
0.7257828504536142                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.74, 'eta': 0.075, 'eval_metric': 'auc', 'gamma': 0.885, 'learning_rate': 0.046200000000000005, 'max_depth': 10, 'min_child_weight': 3.475, 'missing': None, 'n_estimators': 473, 'objective': 'binary:logistic', 'subsample': 0.715, 'tree_method': 'exact'}
0.727758267486099                                                                                                      
{'booster': 'gbtree', 'colsample_bytree': 0.935, 'eta': 0.075, 'eval_metric': 'auc', 'gamma': 0.85, 'learning_rate': 0.0322, 'max_depth': 10, 'min_child_weight': 5.3500000000000005, 'missing': None, 'n_estimators': 604, 'objective': 'binary:logistic', 'subsample': 0.8, 'tree_method': 'exact'}
0.733611354989757                                                                                                      
{'booster': 'gbtree', 'colsample_bytree': 0.595, 'eta': 0.325, 'eval_metric': 'auc', 'gamma': 0.985, 'learning_rate': 0.01, 'max_depth': 8, 'min_child_weight': 3.5500000000000003, 'missing': None, 'n_estimators': 309, 'objective': 'binary:logistic', 'subsample': 0.685, 'tree_method': 'exact'}
0.7329528826455955                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.9400000000000001, 'eta': 0.425, 'eval_metric': 'auc', 'gamma': 0.9500000000000001, 'learning_rate': 0.0347, 'max_depth': 6, 'min_child_weight': 1.225, 'missing': None, 'n_estimators': 524, 'objective': 'binary:logistic', 'subsample': 0.6, 'tree_method': 'exact'}
0.7339771729587358                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.93, 'eta': 0.255, 'eval_metric': 'auc', 'gamma': 0.515, 'learning_rate': 0.0005, 'max_depth': 6, 'min_child_weight': 7.025, 'missing': None, 'n_estimators': 623, 'objective': 'binary:logistic', 'subsample': 0.545, 'tree_method': 'exact'}
0.7311969563944981                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.965, 'eta': 0.225, 'eval_metric': 'auc', 'gamma': 0.55, 'learning_rate': 0.0207, 'max_depth': 6, 'min_child_weight': 1.6500000000000001, 'missing': None, 'n_estimators': 272, 'objective': 'binary:logistic', 'subsample': 0.72, 'tree_method': 'exact'}
0.7324407374890255                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.765, 'eta': 0.295, 'eval_metric': 'auc', 'gamma': 0.99, 'learning_rate': 0.041, 'max_depth': 3, 'min_child_weight': 3.1, 'missing': None, 'n_estimators': 582, 'objective': 'binary:logistic', 'subsample': 0.995, 'tree_method': 'exact'}
0.7325139010828212                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.73, 'eta': 0.035, 'eval_metric': 'auc', 'gamma': 0.74, 'learning_rate': 0.0339, 'max_depth': 5, 'min_child_weight': 4.375, 'missing': None, 'n_estimators': 175, 'objective': 'binary:logistic', 'subsample': 0.765, 'tree_method': 'exact'}
0.733099209833187                                                                                                      
{'booster': 'gbtree', 'colsample_bytree': 0.96, 'eta': 0.15, 'eval_metric': 'auc', 'gamma': 0.91, 'learning_rate': 0.0475, 'max_depth': 4, 'min_child_weight': 8.950000000000001, 'missing': None, 'n_estimators': 152, 'objective': 'binary:logistic', 'subsample': 0.545, 'tree_method': 'exact'}
0.7292947029558092                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.615, 'eta': 0.425, 'eval_metric': 'auc', 'gamma': 0.595, 'learning_rate': 0.0009000000000000001, 'max_depth': 5, 'min_child_weight': 1.5250000000000001, 'missing': None, 'n_estimators': 433, 'objective': 'binary:logistic', 'subsample': 0.725, 'tree_method': 'exact'}
0.7301726660813579                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.53, 'eta': 0.295, 'eval_metric': 'auc', 'gamma': 0.6, 'learning_rate': 0.0085, 'max_depth': 9, 'min_child_weight': 3.0, 'missing': None, 'n_estimators': 149, 'objective': 'binary:logistic', 'subsample': 0.935, 'tree_method': 'exact'}
0.7280509218612818                                                                                                     
{'booster': 'gbtree', 'colsample_bytree': 0.9, 'eta': 0.06, 'eval_metric': 'auc', 'gamma': 0.61, 'learning_rate': 0.0495, 'max_depth': 7, 'min_child_weight': 2.5, 'missing': None, 'n_estimators': 672, 'objective': 'binary:logistic', 'subsample': 0.725, 'tree_method': 'exact'}
0.72585601404741                                                                                                       
{'booster': 'gbtree', 'colsample_bytree': 0.88, 'eta': 0.195, 'eval_metric': 'auc', 'gamma': 0.55, 'learning_rate': 0.0021000000000000003, 'max_depth': 3, 'min_child_weight': 5.95, 'missing': None, 'n_estimators': 170, 'objective': 'binary:logistic', 'subsample': 0.86, 'tree_method': 'exact'}
100%|███████████████████████████████████████████████| 20/20 [01:38<00:00,  4.94s/trial, best loss: 0.26602282704126423]


print('The best parameters of XgBoost:')
print(best)

The best parameters of XgBoost:
{'colsample_bytree': 0.93, 'eta': 0.255, 'gamma': 0.515, 'learning_rate': 0.0005, 'max_depth': 4, 'min_child_weight': 7.025, 'n_estimators': 622, 'subsample': 0.545}


params = space_eval(space_xgb, best)
params

{'booster': 'gbtree',
 'colsample_bytree': 0.93,
 'eta': 0.255,
 'eval_metric': 'auc',
 'gamma': 0.515,
 'learning_rate': 0.0005,
 'max_depth': 6,
 'min_child_weight': 7.025,
 'missing': None,
 'n_estimators': 623,
 'objective': 'binary:logistic',
 'subsample': 0.545,
 'tree_method': 'exact'}


best_params = {'booster': 'gbtree',
 'colsample_bytree': 0.74,
 'eta': 0.25,
 'eval_metric': 'auc',
 'gamma': 0.665,
 'learning_rate': 0.0016,
 'max_depth': 11,
 'min_child_weight': 5.5,
 'missing': None,
 'n_estimators': 673,
 'objective': 'binary:logistic',
 'subsample': 0.58,
 'tree_method': 'exact'}


warnings.filterwarnings("ignore", category=UserWarning)
XGB_Classifier = XGBClassifier(**best_params)
XGB_Classifier.fit(X_train, y_train)
acc_XGB_Classifier = round(XGB_Classifier.score(X_train, y_train) * 100, 2)
# Check train accuracy
acc_XGB_Classifier

75.42


# Make prediction on test set
pred = XGB_Classifier.predict(X_test)


# Plot the Confusion Matrix for Train and Test
print(classification_report(y_test, pred, digits=4))
f, axes = plt.subplots(1, 1, figsize=(8, 4))
axes.set_title('Test Set')
sns.heatmap(confusion_matrix(y_test, pred), 
           annot = True, fmt=".0f", annot_kws={"size": 18})

              precision    recall  f1-score   support

           0     0.7175    0.7810    0.7479      6880
           1     0.7561    0.6884    0.7207      6788

    accuracy                         0.7350     13668
   macro avg     0.7368    0.7347    0.7343     13668
weighted avg     0.7367    0.7350    0.7344     13668

<AxesSubplot:title={'center':'Test Set'}>


# Plot feature importances
fig =  plt.figure(figsize = (15,15))
axes = fig.add_subplot(111)
xgb.plot_importance(XGB_Classifier,ax = axes,height =0.5)
plt.show();
plt.close()


# Saving xgb model
filename = 'xgb.sav'
pickle.dump(XGB_Classifier, open(filename, 'wb'))


# implementing elbow method to find best k 
error_rate = []
for i in range(1,60):
    knn = KNeighborsClassifier(n_neighbors=i)
    knn.fit(X_train,y_train)
    pred_i = knn.predict(X_test)
    error_rate.append(np.mean(pred_i != y_test))

plt.figure(figsize=(10,6))
plt.plot(range(1,60),error_rate,color='blue', linestyle='dashed', marker='o',markerfacecolor='red', markersize=10)
plt.title('Error Rate vs. K Value')
plt.xlabel('K')
plt.ylabel('Error Rate')
print("Minimum error:",min(error_rate),"at K =",error_rate.index(min(error_rate)))

Minimum error: 0.27158326016973955 at K = 44


knn = KNeighborsClassifier(n_neighbors=44)
knn.fit(X_train,y_train)
knn_pred = knn.predict(X_test)

# Plot the Confusion Matrix for Train and Test
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
print(classification_report(y_test, knn_pred, digits=4))
f, axes = plt.subplots(1, 1, figsize=(8, 4))
axes.set_title('Test Set')
sns.heatmap(confusion_matrix(y_test, knn_pred), 
           annot = True, fmt=".0f", annot_kws={"size": 18})

              precision    recall  f1-score   support

           0     0.7078    0.7810    0.7426      6880
           1     0.7520    0.6732    0.7105      6788

    accuracy                         0.7275     13668
   macro avg     0.7299    0.7271    0.7265     13668
weighted avg     0.7298    0.7275    0.7266     13668

<AxesSubplot:title={'center':'Test Set'}>


# Saving knn model
filename = 'knn.sav'
pickle.dump(knn, open(filename, 'wb'))


svc = SVC(probability=True)
svc.fit(X_train,y_train)
svc_pred = svc.predict(X_test)

# Plot the Confusion Matrix for Train and Test
print(classification_report(y_test, svc_pred, digits=4))
f, axes = plt.subplots(1, 1, figsize=(8, 4))
axes.set_title('Test Set')
sns.heatmap(confusion_matrix(y_test, svc_pred), 
           annot = True, fmt=".0f", annot_kws={"size": 18})

              precision    recall  f1-score   support

           0     0.7101    0.7817    0.7442      6880
           1     0.7535    0.6765    0.7129      6788

    accuracy                         0.7294     13668
   macro avg     0.7318    0.7291    0.7285     13668
weighted avg     0.7316    0.7294    0.7286     13668

<AxesSubplot:title={'center':'Test Set'}>


# Saving svc model
filename = 'svc.sav'
pickle.dump(svc, open(filename, 'wb'))


# Since svc does not have a feature_importances_ function, we will use permutation_imporatnce from sklearn instead
# This method changes the data in a feature column and then tests how much that affects the model accuracy

perm_importance = permutation_importance(svc, X_test, y_test)

feature_names = X_train.columns
features = np.array(feature_names)

sorted_idx = perm_importance.importances_mean.argsort()
plt.barh(features[sorted_idx], perm_importance.importances_mean[sorted_idx])
plt.xlabel("Permutation Importance")

Text(0.5, 0, 'Permutation Importance')


# Number of features
X_train.shape

(54668, 13)


X_train, X_val, y_train, y_val = train_test_split(X_train,y_train,test_size=0.20)

nn = Sequential()
nn.add(Dense(13,activation='relu')) # number of neurons = number of features
nn.add(Dense(50,activation='relu',kernel_initializer=tf.random_uniform_initializer(minval=-0.1, maxval=0.1), 
    bias_initializer=tf.random_uniform_initializer(minval=-0.1, maxval=0.1)))
nn.add(Dropout(0.2))
nn.add(Dense(50,activation='relu',kernel_initializer=tf.random_uniform_initializer(minval=-0.1, maxval=0.1),
    bias_initializer=tf.random_uniform_initializer(minval=-0.1, maxval=0.1)))
nn.add(Dropout(0.2))
nn.add(Dense(50,activation='relu',kernel_initializer=tf.random_uniform_initializer(minval=-0.1, maxval=0.1),
    bias_initializer=tf.random_uniform_initializer(minval=-0.1, maxval=0.1)))
nn.add(Dropout(0.2))
nn.add(Dense(1,activation='sigmoid'))

nn.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

early_stop = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=5)

nn.fit(x=X_train.values,y=y_train.values,
          validation_data=(X_val,y_val.values),
          batch_size=100,epochs=150,callbacks=[early_stop])

Epoch 1/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5765 - accuracy: 0.7111 - val_loss: 0.5536 - val_accuracy: 0.7312
Epoch 2/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5575 - accuracy: 0.7262 - val_loss: 0.5503 - val_accuracy: 0.7318
Epoch 3/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5540 - accuracy: 0.7268 - val_loss: 0.5476 - val_accuracy: 0.7316
Epoch 4/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5532 - accuracy: 0.7277 - val_loss: 0.5458 - val_accuracy: 0.7353
Epoch 5/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5527 - accuracy: 0.7277 - val_loss: 0.5462 - val_accuracy: 0.7335
Epoch 6/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5516 - accuracy: 0.7284 - val_loss: 0.5457 - val_accuracy: 0.7342
Epoch 7/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5517 - accuracy: 0.7287 - val_loss: 0.5458 - val_accuracy: 0.7336
Epoch 8/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5506 - accuracy: 0.7295 - val_loss: 0.5471 - val_accuracy: 0.7305
Epoch 9/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5507 - accuracy: 0.7294 - val_loss: 0.5442 - val_accuracy: 0.7337
Epoch 10/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5506 - accuracy: 0.7295 - val_loss: 0.5457 - val_accuracy: 0.7361
Epoch 11/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5492 - accuracy: 0.7300 - val_loss: 0.5442 - val_accuracy: 0.7348
Epoch 12/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5500 - accuracy: 0.7303 - val_loss: 0.5441 - val_accuracy: 0.7353
Epoch 13/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5489 - accuracy: 0.7299 - val_loss: 0.5433 - val_accuracy: 0.7372
Epoch 14/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5493 - accuracy: 0.7305 - val_loss: 0.5457 - val_accuracy: 0.7317
Epoch 15/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5484 - accuracy: 0.7310 - val_loss: 0.5433 - val_accuracy: 0.7350
Epoch 16/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5493 - accuracy: 0.7290 - val_loss: 0.5440 - val_accuracy: 0.7308
Epoch 17/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5487 - accuracy: 0.7313 - val_loss: 0.5449 - val_accuracy: 0.7355
Epoch 18/150
438/438 [==============================] - 1s 2ms/step - loss: 0.5473 - accuracy: 0.7303 - val_loss: 0.5439 - val_accuracy: 0.7357
Epoch 00018: early stopping

<keras.callbacks.History at 0x267183efc70>


# print model structure
nn.summary()

Model: "sequential"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 dense (Dense)               (None, 13)                182       
                                                                 
 dense_1 (Dense)             (None, 50)                700       
                                                                 
 dropout (Dropout)           (None, 50)                0         
                                                                 
 dense_2 (Dense)             (None, 50)                2550      
                                                                 
 dropout_1 (Dropout)         (None, 50)                0         
                                                                 
 dense_3 (Dense)             (None, 50)                2550      
                                                                 
 dropout_2 (Dropout)         (None, 50)                0         
                                                                 
 dense_4 (Dense)             (None, 1)                 51        
                                                                 
=================================================================
Total params: 6,033
Trainable params: 6,033
Non-trainable params: 0
_________________________________________________________________


losses = pd.DataFrame(nn.history.history)
losses[['loss','val_loss']].plot();


threshold = 0.5
dnn_pred = nn.predict(X_test)
dnn_pred = np.where(dnn_pred > threshold, 1,0)
print(classification_report(y_test,dnn_pred, digits=4))
# Plot the Confusion Matrix for Train and Test
f, axes = plt.subplots(1, 1, figsize=(8, 4))
axes.set_title('Test Set')
sns.heatmap(confusion_matrix(y_test, dnn_pred), 
           annot = True, fmt=".0f", annot_kws={"size": 18})

              precision    recall  f1-score   support

           0     0.7304    0.7330    0.7317      6880
           1     0.7284    0.7258    0.7271      6788

    accuracy                         0.7294     13668
   macro avg     0.7294    0.7294    0.7294     13668
weighted avg     0.7294    0.7294    0.7294     13668

<AxesSubplot:title={'center':'Test Set'}>


# Saving neural network model
nn.save("nnmodel")

INFO:tensorflow:Assets written to: nnmodel\assets


print('size of X_test: ', X_test.shape)
print('size of y_test: ', y_test.shape)

size of X_test:  (13668, 13)
size of y_test:  (13668,)


# we take 30% of this as test set
split = round(X_test.shape[0]*0.7)
split

9568


X_valme = X_test[:split].reset_index().drop('index', axis=1)
X_testme = X_test[split:].reset_index().drop('index', axis=1)
y_valme = y_test[:split].reset_index().drop('index', axis=1)
y_testme = y_test[split:].reset_index().drop('index', axis=1)


val_pred1=XGB_Classifier.predict_proba(X_valme)
test_pred1=XGB_Classifier.predict_proba(X_testme)
val_pred1=pd.DataFrame(pd.DataFrame(val_pred1)[1])
test_pred1=pd.DataFrame(pd.DataFrame(test_pred1)[1])


val_pred2=knn.predict_proba(X_valme)
test_pred2=knn.predict_proba(X_testme)
val_pred2=pd.DataFrame(pd.DataFrame(val_pred2)[1])
val_pred2.rename(columns={1:'2'}, inplace=True)
test_pred2=pd.DataFrame(pd.DataFrame(test_pred2)[1])
test_pred2.rename(columns={1:'2'}, inplace=True)


val_pred3=svc.predict_proba(X_valme)
test_pred3=svc.predict_proba(X_testme)
val_pred3=pd.DataFrame(pd.DataFrame(val_pred3)[1])
val_pred3.rename(columns={1:'3'}, inplace=True)
test_pred3=pd.DataFrame(pd.DataFrame(test_pred3)[1])
test_pred3.rename(columns={1:'3'}, inplace=True)


val_pred4=nn.predict(X_valme)
test_pred4=nn.predict(X_testme)
val_pred4=pd.DataFrame(val_pred4, columns = ['4'])
test_pred4=pd.DataFrame(test_pred4, columns = ['4'])


df_val=pd.concat([X_valme,val_pred1,val_pred2,val_pred3,val_pred4],axis=1)
df_test=pd.concat([X_testme,test_pred1,test_pred2,test_pred3,test_pred4],axis=1)

df_val


from sklearn.linear_model import LogisticRegression
logreg = LogisticRegression(max_iter=400)
logreg.fit(df_val,np.ravel(y_valme)) # make y_valme into 1-d array
pred = logreg.predict(df_test)
print(classification_report(y_testme, pred, digits=4))
# Plot the Confusion Matrix for Train and Test
f, axes = plt.subplots(1, 1, figsize=(8, 4))
axes.set_title('Test Set')
sns.heatmap(confusion_matrix(y_testme, pred), 
           annot = True, fmt=".0f", annot_kws={"size": 18})

              precision    recall  f1-score   support

           0     0.7177    0.7648    0.7405      2054
           1     0.7473    0.6979    0.7218      2046

    accuracy                         0.7315      4100
   macro avg     0.7325    0.7314    0.7311      4100
weighted avg     0.7324    0.7315    0.7312      4100

<AxesSubplot:title={'center':'Test Set'}>


# Comparing with our current best model: XGB_CLassifier...
temppred = XGB_Classifier.predict(X_testme)
print(classification_report(y_testme, temppred, digits=4))
# Plot the Confusion Matrix for Train and Test
f, axes = plt.subplots(1, 1, figsize=(8, 4))
axes.set_title('Test Set')
sns.heatmap(confusion_matrix(y_testme, temppred), 
           annot = True, fmt=".0f", annot_kws={"size": 18})

              precision    recall  f1-score   support

           0     0.7095    0.7824    0.7442      2054
           1     0.7564    0.6784    0.7153      2046

    accuracy                         0.7305      4100
   macro avg     0.7329    0.7304    0.7297      4100
weighted avg     0.7329    0.7305    0.7297      4100

<AxesSubplot:title={'center':'Test Set'}>


# Saving ensemble model
filename = 'logreg.sav'
pickle.dump(logreg, open(filename, 'wb'))


print("Hi! We will let you know your risk for cardiovascular disease according to the following indicators, do follow through and give us a shot!\n")
time.sleep(1)

data = {}
data['year'] = int(input("Current age (year): "))
data['gender'] = int(input("Gender (0 for female and 1 for male): "))
data['height'] = float(input("Height (m): "))
data['weight'] = float(input("Weight (kg): "))
data['ap_hi'] = float(input('Systolic bloood pressure (mmHg): '))
data['ap_lo'] = float(input('Diastolic bloood pressure (mmHg): '))
data['map'] = float((data['ap_hi']+2*data['ap_lo'])/3)
data['pp'] = float(data['ap_hi'] - data['ap_lo'])
data['cholesterol'] = int(input('Cholestrol level (1 for normal, 2 for above normal, 3 for well above normal): '))
data['gluc'] = int(input('Blood glucose level (1 for normal, 2 for above normal, 3 for well above normal): '))
data['bmi'] = float(data['weight']/data['height']**2)
data['active'] = int(input('Excercise Regularly? (0 for no, 1 for yes): '))
data['diabetes'] = int(input('Diabetes (0 for no, 1 for yes): '))

Hi! We will let you know your risk for cardiovascular disease according to the following indicators, do follow through and give us a shot!

Current age (year): 60
Gender (0 for female and 1 for male): 1
Height (m): 1.8
Weight (kg): 90
Systolic bloood pressure (mmHg): 160
Diastolic bloood pressure (mmHg): 100
Cholestrol level (1 for normal, 2 for above normal, 3 for well above normal): 3
Blood glucose level (1 for normal, 2 for above normal, 3 for well above normal): 3
Excercise Regularly? (0 for no, 1 for yes): 0
Diabetes (0 for no, 1 for yes): 1


pred_df = pd.DataFrame(data=[[v for k, v in data.items()]], columns=[key for key in data])
pred_df


scaler = pickle.load(open('scaler.sav', 'rb'))
to_be_scaled_feat = ['year', 'height', 'weight', 'ap_hi', 'ap_lo', 'map', 'pp', 'bmi']
pred_df[to_be_scaled_feat] = scaler.transform(pred_df[to_be_scaled_feat])
pred_df


# loading all models
XGB_Classifier = pickle.load(open('xgb.sav', 'rb'))
knn = pickle.load(open('knn.sav', 'rb'))
svc = pickle.load(open('svc.sav', 'rb'))
nn = tf.keras.models.load_model("nnmodel")
logreg = pickle.load(open('logreg.sav', 'rb'))

# making predictions with each model
pred1=XGB_Classifier.predict_proba(pred_df)
pred1=pd.DataFrame(pd.DataFrame(pred1)[1])

pred2=knn.predict_proba(pred_df)
pred2=pd.DataFrame(pd.DataFrame(pred2)[1])
pred2.rename(columns={1:'2'}, inplace=True)

pred3=svc.predict_proba(pred_df)
pred3=pd.DataFrame(pd.DataFrame(pred3)[1])
pred3.rename(columns={1:'3'}, inplace=True)

pred4=nn.predict(pred_df)
pred4=pd.DataFrame(pred4, columns = ['4'])

# concatenating indicidual model predictions with user data 
pred_test=pd.concat([pred_df,pred1,pred2,pred3,pred4],axis=1)

# making ensembled prediction
risk = logreg.predict_proba(pred_test)[0][1]


if (risk<=0.5):
    print('Your risk for cardiovasvular disease is', round(risk*100, 2), '%', ', keep it up!')
else:
    if (risk<0.7):
        print('Your risk for cardiovasvular disease is', round(risk*100, 2), '%', ', please take action to pull your health back on track!')
    else:
        print('Your risk for cardiovasvular disease is', round(risk*100, 2), '%', ', please visit the doctor immediately for a thorough diagnosis!')
  
    if(data['ap_hi'] > 120):
        print('You are at risk of hypertension, you can visit this recommended website for some advice: https://www.mayoclinic.org/diseases-conditions/high-blood-pressure/in-depth/high-blood-pressure/art-20046974')
    if(data['cholesterol'] > 1):
        print('You are at risk of high cholesterol, you can visit this recommended website for some advice: https://www.mayoclinic.org/diseases-conditions/high-blood-cholesterol/in-depth/reduce-cholesterol/art-20045935')
    if(data['bmi']>=25):
        print('You are overweight, you can visit this recommended website for some advice: https://reverehealth.com/live-better/tips-to-maintain-a-healthy-weight/')
    if(data['bmi']<18.5):
        print('You are underweight, you can visit this recommended website for some advice: https://rb.gy/hurwan')

Your risk for cardiovasvular disease is 91.49 % , please visit the doctor immediately for a thorough diagnosis!
You are at risk of hypertension, you can visit this recommended website for some advice: https://www.mayoclinic.org/diseases-conditions/high-blood-pressure/in-depth/high-blood-pressure/art-20046974
You are at risk of high cholesterol, you can visit this recommended website for some advice: https://www.mayoclinic.org/diseases-conditions/high-blood-cholesterol/in-depth/reduce-cholesterol/art-20045935
You are overweight, you can visit this recommended website for some advice: https://reverehealth.com/live-better/tips-to-maintain-a-healthy-weight/

	id	age	gender	height	weight	ap_hi	ap_lo	cholesterol	gluc	smoke	alco	active	cardio
count	70000.000000	70000.000000	70000.000000	70000.000000	70000.000000	70000.000000	70000.000000	70000.000000	70000.000000	70000.000000	70000.000000	70000.000000	70000.000000
mean	49972.419900	19468.865814	1.349571	164.359229	74.205690	128.817286	96.630414	1.366871	1.226457	0.088129	0.053771	0.803729	0.499700
std	28851.302323	2467.251667	0.476838	8.210126	14.395757	154.011419	188.472530	0.680250	0.572270	0.283484	0.225568	0.397179	0.500003
min	0.000000	10798.000000	1.000000	55.000000	10.000000	-150.000000	-70.000000	1.000000	1.000000	0.000000	0.000000	0.000000	0.000000
25%	25006.750000	17664.000000	1.000000	159.000000	65.000000	120.000000	80.000000	1.000000	1.000000	0.000000	0.000000	1.000000	0.000000
50%	50001.500000	19703.000000	1.000000	165.000000	72.000000	120.000000	80.000000	1.000000	1.000000	0.000000	0.000000	1.000000	0.000000
75%	74889.250000	21327.000000	2.000000	170.000000	82.000000	140.000000	90.000000	2.000000	1.000000	0.000000	0.000000	1.000000	1.000000
max	99999.000000	23713.000000	2.000000	250.000000	200.000000	16020.000000	11000.000000	3.000000	3.000000	1.000000	1.000000	1.000000	1.000000

	height	weight	ap_hi	ap_lo
count	68340.000000	68340.000000	68340.000000	68340.000000
mean	164.456292	73.795437	126.632309	81.247261
std	7.591273	12.996633	16.471926	9.417500
min	144.000000	46.000000	12.000000	1.000000
25%	159.000000	65.000000	120.000000	80.000000
50%	165.000000	72.000000	120.000000	80.000000
75%	170.000000	82.000000	140.000000	90.000000
max	187.000000	116.000000	309.000000	182.000000

	principal component 1	principal component 2	label
0	-2.014826	1.506569	0.0
1	2.428809	-1.877420	1.0
2	-0.326738	-0.834095	1.0
3	2.621867	1.968769	1.0
4	-3.853166	-1.121575	0.0
...	...	...	...
68331	1.887469	-0.134695	1.0
68332	-0.618706	1.292674	0.0
68333	5.728409	2.324621	1.0
68334	0.736180	-0.850707	1.0
68335	-0.563241	-0.136935	0.0

	Pregnancies	Glucose	BloodPressure	SkinThickness	Insulin	BMI	DiabetesPedigreeFunction	Age	Outcome
0	6	148.0	72.0	35.0	169.5	33.6	0.627	50	1
1	1	85.0	66.0	29.0	102.5	26.6	0.351	31	0

	Pregnancies	Glucose	map	SkinThickness	Insulin	bmi	DiabetesPedigreeFunction	year	Outcome
count	768.000000	768.000000	768.000000	768.000000	768.000000	768.000000	768.000000	768.000000	768.000000
mean	3.845052	121.677083	72.389323	29.089844	141.753906	32.434635	0.471876	33.240885	0.348958
std	3.369578	30.464161	12.106039	8.890820	89.100847	6.880498	0.331329	11.760232	0.476951
min	0.000000	44.000000	24.000000	7.000000	14.000000	18.200000	0.078000	21.000000	0.000000
25%	1.000000	99.750000	64.000000	25.000000	102.500000	27.500000	0.243750	24.000000	0.000000
50%	3.000000	117.000000	72.000000	28.000000	102.500000	32.050000	0.372500	29.000000	0.000000
75%	6.000000	140.250000	80.000000	32.000000	169.500000	36.600000	0.626250	41.000000	1.000000
max	17.000000	199.000000	122.000000	99.000000	846.000000	67.100000	2.420000	81.000000	1.000000

	id	age	gender	height	weight	ap_hi	ap_lo	cholesterol	gluc	active	cardio
0	0	18393	2	168	62.0	110	80	1	1	1	0
1	1	20228	1	156	85.0	140	90	3	1	1	1
2	2	18857	1	165	64.0	130	70	3	1	0	1
3	3	17623	2	169	82.0	150	100	1	1	1	1
4	4	17474	1	156	56.0	100	60	1	1	0	0

	age	gender	height	weight	ap_hi	ap_lo	cholesterol	gluc	active	cardio
10494	16937	2	170	70.0	120	80	1	1	0	0
44653	16937	2	170	70.0	120	80	1	1	0	0
1142	17493	2	169	74.0	120	80	1	1	1	1
50432	17493	2	169	74.0	120	80	1	1	1	1
32683	17535	2	165	65.0	120	80	1	1	1	0

	year	gender	height	weight	ap_hi	ap_lo	cholesterol	gluc	smoke	alco	active	cardio
0	50	2	168	62.0	110.0	80.0	1	1	0	0	1	0
1	55	1	156	85.0	140.0	90.0	3	1	0	0	1	1
2	52	1	165	64.0	130.0	70.0	3	1	0	0	0	1
3	48	2	169	82.0	150.0	100.0	1	1	0	0	1	1
4	48	1	156	56.0	100.0	60.0	1	1	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...
69995	53	2	168	76.0	120.0	80.0	1	1	1	0	1	0
69996	62	1	158	126.0	140.0	90.0	2	2	0	0	1	1
69997	52	2	183	105.0	180.0	90.0	3	1	0	1	0	1
69998	61	1	163	72.0	135.0	80.0	1	2	0	0	0	1
69999	56	1	170	72.0	120.0	80.0	2	1	0	0	1	0

	year	gender	height	weight	ap_hi	ap_lo	map	pp	cholesterol	gluc	bmi	active	cardio
count	68336.000000	68336.000000	68336.000000	68336.000000	68336.000000	68336.000000	68336.000000	68336.000000	68336.000000	68336.000000	68336.000000	68336.000000	68336.000000
mean	53.351030	0.349962	164.456129	73.795820	126.633136	81.247773	96.376227	45.385363	1.364654	1.224552	27.329075	0.803852	0.498361
std	6.755641	0.476961	7.591233	12.996457	16.471932	9.417324	10.928723	11.643811	0.679032	0.570477	4.800928	0.397085	0.500001
min	39.000000	0.000000	144.000000	46.000000	12.000000	1.000000	12.000000	-69.272565	1.000000	1.000000	14.609204	0.000000	0.000000
25%	48.000000	0.000000	159.000000	65.000000	120.000000	80.000000	93.333333	40.000000	1.000000	1.000000	23.875115	1.000000	0.000000
50%	54.000000	0.000000	165.000000	72.000000	120.000000	80.000000	93.333333	40.000000	1.000000	1.000000	26.346494	1.000000	0.000000
75%	58.000000	1.000000	170.000000	82.000000	140.000000	90.000000	103.333333	50.000000	1.000000	1.000000	30.094730	1.000000	1.000000
max	65.000000	1.000000	187.000000	116.000000	309.000000	182.000000	186.666667	227.727435	3.000000	3.000000	55.459105	1.000000	1.000000

	Pregnancies	Glucose	map	SkinThickness	Insulin	bmi	DiabetesPedigreeFunction	year	Outcome
count	219.000000	219.000000	219.000000	219.000000	219.000000	219.000000	219.000000	219.000000	219.000000
mean	6.657534	131.456621	77.650685	30.666667	155.511416	33.013699	0.474548	49.045662	0.506849
std	3.537035	32.280333	10.932241	8.324460	92.092189	6.153413	0.323434	8.579243	0.501098
min	0.000000	57.000000	50.000000	7.000000	22.000000	19.600000	0.085000	39.000000	0.000000
25%	5.000000	106.000000	71.000000	27.000000	102.500000	28.750000	0.241000	42.000000	0.000000
50%	7.000000	129.000000	76.000000	30.000000	145.000000	32.900000	0.376000	46.000000	1.000000
75%	9.000000	154.000000	84.000000	32.000000	169.500000	37.100000	0.643500	54.000000	1.000000
max	17.000000	197.000000	114.000000	99.000000	846.000000	52.300000	1.781000	81.000000	1.000000

	year	gender	height	weight	ap_hi	ap_lo	map	pp	cholesterol	gluc	bmi	active	diabetes	1	2	3	4
0	-1.681125	1	1.385465	0.401675	-1.011988	-1.196711	-1.196471	-0.463477	1	1	-0.316177	1	1	0.282230	0.159091	0.237879	0.097264
1	-0.348191	0	-0.852790	-0.290187	2.029628	0.932943	1.556653	2.112755	3	1	0.151425	1	1	0.717679	0.795455	0.800479	0.876998
2	-1.088710	1	0.727154	-0.290187	-0.403665	-0.664297	-0.584665	-0.034105	1	1	-0.644195	1	0	0.322638	0.181818	0.248494	0.168152
3	1.577158	0	-0.984453	1.554780	0.204658	-1.196711	-0.584665	1.254011	1	1	2.254586	0	0	0.594198	0.613636	0.794284	0.666422
4	-1.977332	1	2.043775	0.478549	-0.403665	-0.131884	-0.278763	-0.463477	1	1	-0.546297	1	0	0.277076	0.068182	0.246439	0.137461
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
9563	0.688536	0	-0.852790	0.017307	-1.011988	-1.196711	-1.196471	-0.463477	1	1	0.485243	1	1	0.345271	0.386364	0.223267	0.287999
9564	-0.792502	0	-0.589466	1.247286	0.812982	0.826460	0.883667	0.481142	1	1	1.633917	1	0	0.697855	0.772727	0.802976	0.817462
9565	-0.051983	0	0.068844	-0.213314	-0.403665	-0.131884	-0.278763	-0.463477	2	2	-0.257207	0	1	0.419890	0.431818	0.327862	0.428781
9566	0.836640	1	0.858816	-0.443935	0.204658	-1.196711	-0.584665	1.254011	3	3	-0.845538	1	0	0.583336	0.568182	0.767781	0.703968
9567	0.392328	0	-0.062818	1.247286	1.421305	-0.131884	0.638945	2.112755	1	1	1.280991	0	1	0.723287	0.772727	0.816515	0.824921

EE0005 Mini Project¶

Outline¶

1. Introduction¶

2. New Knowlege we Have Learned¶

3. Contribution¶

4. Importing Libraries¶

5. Exploratory Data Analysis and Data Cleaning¶

Overall Statistical Description¶

Checking for Null Values¶

Checking for Dataset Imbalance¶

Data Cleaning and Data Preparation¶

Dealing with illogical ap_hi and ap_lo values¶

Dealing with Outliers¶

Feature Engineering¶

Visualization¶

Separating categorical variables from numerical variables¶

Standard Statistical Distributions for Numerical Variables¶

Distribution of Age Variable¶

Creating Mutual Box Plots between Numerical Variables and Presence of Cardiovascular Disease¶

Checking the Distributions of Categorical Variables¶

Analysing Relationship Between Gender and Presence of Cardiovascular Disease¶

Analysing Relationship Between Cholesterol and Presence of Cardiovascular Disease¶

Analysing Relationship Between Glucose and Presence of Cardiovascular Disease¶

Analysing Relationship Between Smoke and Presence of Cardiovascular Disease¶

Analysing Relationship Between Alcohol and Presence of Cardiovascular Disease¶

Analysing Relationship Between Active and Presence of Cardiovascular Disease¶

Compute pairwise correlation of variables¶

PCA Analysis¶

Data Merge¶

We found this dataset because many researches showed that diabetes is a great factor causing cardiovascular disease. We want to introduce the “diabetes” value into our cardio dataset. (After adding this variable, the accuracy of predictions on our main cardiovasuclar disease dataset improved)¶

Dealing with Illogical Values in Data¶

Predict the Diabetes Outcome in Our Main Dataset¶

Model Training and Testing¶

Data Preparation¶

Decision Tree Classifier¶

Random Forest Classifier¶

XGBoost¶

Analysis of Decision Tree, Random Forest & XGBoost Classifiers¶

K-Nearest Neighbours¶

Support Vector Machine¶

Neural Network¶

Model Ensembling - Blending¶

Real-time model prediction¶